© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 216
    Prev
    Next
    INDEX
    Explanations

    words related to promotions or bonuses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    966
    +0.07
    0.2%
    50
    +0.06
    0.2%
    25
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    585
    +0.07
    0.02
    368
    +0.06
    0.02
    117
    +0.06
    0.02
    Negative Logits
    <bos>
    -0.97
    ⓧ
    -0.59
    public
    -0.57
    ૈ
    -0.54
    //
    -0.54
     become
    -0.52
    /*
    -0.52
    //
    -0.52
    ੱਚ
    -0.52
    protected
    -0.51
    POSITIVE LOGITS
     starter
    2.49
     Starter
    2.39
    Starter
    2.12
     starters
    2.06
    starter
    2.04
     affor
    1.25
     lidl
    1.23
     stockholm
    1.22
     maneu
    1.14
     scrat
    1.12
    Activations Density 0.121%

    No Known Activations